Clustering web page addresses for website analysis

A computer system for improving fraud detection algorithms through clustering of web page URLs comprising:

• one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more computer-readable tangible storage media for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising:
• obtaining user flow data associated with a first browsing session at the website, the user flow data including a plurality of web page identifiers;
• generating a web page record for each of the web page identifiers, each web page record including one or more words of the corresponding web page identifier;
• receiving two or more clusters of web page identifiers, wherein the two or more clusters of web page identifiers were output from a machine learning clustering process;
• for each of the web page records, identifying a cluster of web page identifiers by mapping the web page record to one of the two or more clusters of web page identifiers using the machine learning clustering process;
• for each of the web page records, identifying one or more valuable web page identifiers, wherein the valuable web page identifiers are not sent to the machine learning clustering process and are not included in any cluster of web page identifiers;
• and
• constructing a first directed graph representative of the first browsing session, wherein directed edges of the first directed graph are transitions between web pages and one or more nodes of the first directed graph include the identified clusters of web page identifiers and the valuable web page identifiers.

A computer program product for improving fraud detection algorithms through clustering of web page URLs comprising:

• a computer-readable storage device storing computer-readable program code embodied therewith, the computer-readable program code comprising program code executable by a computer to perform a method comprising:
• obtaining user flow data associated with a first browsing session at the website, the user flow data including a plurality of web page identifiers;
• generating a web page record for each of the web page identifiers, each web page record including one or more words of the corresponding web page identifier;
• receiving two or more clusters of web page identifiers, wherein the two or more clusters of web page identifiers were output from a machine learning clustering process;
• for each of the web page records, identifying a cluster of web page identifiers by mapping the web page record to one of the two or more clusters of web page identifiers using the machine learning clustering process;
• for each of the web page records, identifying one or more valuable web page identifiers, wherein the valuable web page identifiers are not sent to the machine learning clustering process and are not included in any cluster of web page identifiers;
• and
• constructing a first directed graph representative of the first browsing session, wherein directed edges of the first directed graph are transitions between web pages and one or more nodes of the first directed graph include the identified clusters of web page identifiers and the valuable web page identifiers.